Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
SpeechT5_pytorch
Commits
fe19a472
Commit
fe19a472
authored
Aug 23, 2024
by
changhl
Browse files
update readme
parent
ca5cf161
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
1 addition
and
1 deletion
+1
-1
README.md
README.md
+1
-1
images/algorithm.png
images/algorithm.png
+0
-0
No files found.
README.md
View file @
fe19a472
...
...
@@ -22,7 +22,7 @@ speechT5的核心是一个常规的**Transformer编码器-解码器**,为了
在预训练期间,同时使用所有的 per-nets 和 post-nets 。预训练后,整个编码器 - 解码器主干在单个任务上进行微调。这种经过微调的模型仅使用特定于给定任务的 per-nets 和 post-nets 。
*例如:要将 SpeechT5 用于文本到语音转换,您需要将文本编码器 per-nets 交换为文本输入,将语音解码器 per-nets 和 post-nets 交换为语音输出。*
<div
align=
"center"
>
<img
src=
"./images/
principle_
algorithm.png"
/>
<img
src=
"./images/algorithm.png"
/>
</div>
**注意: 即使微调模型一开始使用共享预训练模型的同一组权重,但最终版本最终还是完全不同。例如,您不能采用经过微调的 ASR 模型并换掉 per-nets 和 post-nets 来获得有效的 TTS 模型。SpeechT5 很灵活,但不是那么灵活。**
...
...
images/
Principle_
algorithm.png
→
images/algorithm.png
View file @
fe19a472
File moved
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment